Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

1122 · Feb 202519922001200920172026
13 results for MNL-Bandit

Study MNL-Bandit in non-stationary settings with optimal regret bound.

problem Optimizing decisions in a non-stationary environment for multi-armed bandit problems.
method Develops an algorithm with worst-case expected regret bound and introduces new techniques to handle non-stationarity.
result Optimal regret bound proven for the MNL-Bandit problem in non-stationary environments.

Optimal design for multinomial logit models improves assortment selection efficiency.

problem Optimal experimental design for multinomial logit models with feedback.
method Two complementary approaches: MILP reformulation and lifted design.
result Achieves statistical efficiency and scalability for MNL bandits.

Improved online confidence bounds for multinomial logistic models in bandits.

problem Achieving optimal regret in multinomial logistic bandits with bounded parameters and outcomes.
method Deriving an improved online confidence bound and proposing OFU-MNL++ and OFU-MN2^2L algorithms.
result Achieved variance-dependent optimal regret for MNL bandits.

DMNL bandits optimize assortment choices balancing relevance and diversity.

problem Balancing relevance-driven choice with within-assortment diversity.
method Augments MNL choice probabilities with a submodular diversity function, proposing a white-box UCB-based algorithm.
result Achieves at least a (11e+1)(1-\frac{1}{e+1})-approximate regret bound of $ ilde{O}\left(d \sqrt{T/K} ight)$.

Paper tackles combinatorial reinforcement learning with preference feedback.

problem Modeling long-term user engagement in scenarios like recommender systems and online advertising.
method Assumes a contextual MNL preference model with linear mean utilities and approximates item values. Proposes MNL-VQL algorithm.
result Achieves nearly minimax-optimal regret for linear MDPs with preference feedback.

New algorithm tackles non-linear utility in MNL bandits with ildeO(T) ilde{O}(\sqrt{T}) regret.

problem Sequential assortment selection with intricate user-item interactions.
method Upper Confidence Bound principle for non-linear parametric utility functions, including neural networks.
result Achieves ildeO(T) ilde{O}(\sqrt{T}) regret bound for neural network-based utilities.